visiongemma for LangChain
io.github.q1023884985/visiongemma
Local AI vision MCP server for Windows: OCR, chart analysis, scene description. 100% offline.
client:LangChain
transport:stdio
runtime:pypi
Install visiongemma in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"visiongemma": {
"transport": "stdio",
"command": "uvx",
"args": ["visiongemma-mcp"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs